GraphNews

📣 Foundation models for graph reasoning become even stronger - in our new NeurIPS 2024 work we introduce UltraQuery: going beyond simple one-hop link…

As a technology SME in the KM space, I am excited about the changes happening in the semantic software industry. Just two years ago, in my book, I provided a complete analysis of the leading providers of taxonomy and ontology management systems, as well as graph providers, auto-tagging systems, and more. While the software products I evaluated are still around, most of them have new owners.

RDF vs LPG: Friends or Foes? For over a decade, ever since #KnowledgeGraphs (KGs) gained prominence, there has been intense competition between #RDF (also…

After a period of more than a year (can't believe time flew by so quick!), I had the pleasure of going back for a second time on the Practical AI Podcast with…

We have some pretty exciting news! We have filed an international patent on our new graph database query algorithm. We have also done some further benchmarking tests, and the results are pretty astounding.

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

Cosdata: A cutting-edge AI data platform for next-gen search pipelines. Features semantic search, knowledge graphs, hybrid capabilities, real-time scalability, and ML integration. Designed for immu...

Recently, knowledge-graph-enhanced recommendation systems have attracted much attention, since knowledge graph (KG) can help improving the dataset quality and offering rich semantics for explainable recommendation. However, current KG-enhanced solutions focus on analyzing user behaviors on the product level and lack effective approaches to extract user preference towards product category, which is essential for better recommendation because users shopping online normally have strong preference towards distinctive product categories, not merely on products, according to various user studies. Moreover, the existing pure embedding-based recommendation methods can only utilize KGs with a limited size, which is not adaptable to many real-world applications. In this paper, we generalize the recommendation problem with preference mining as a compound knowledge reasoning task and propose a novel multi-agent system, called Mcore, which can promote model performance by mining users’ high-level interests and is adaptable to large KGs. Specifically, we split the overall problem and allocate sub-task to each agent: Coordinate Agent takes charge of recognizing the product-category preference of current user, while Relation Agent and Entity Agent perform KG reasoning cooperatively from a user node towards the preferred categories and terminate at a product node as recommendation. To train this heterogeneous multi-agent system, where agents own various functionalities, we propose an asynchronous reinforcement training pipeline, called Multi-agent Collaborative Learning. The extensive experiments on real datasets demonstrate the effectiveness and adaptability of Mcore on recommendation tasks.

In this work, we achieve perfect neural execution of several algorithms by forcing the node and edge representations to be from a fixed finite set. Also, the proposed architectural choice allows us to prove the correctness of the learned algorithms for any test data.

Author Dan Selman shows how easy it is to implement convert natural language text to nodes and edges in a knowledge graph using a new class and method in his demonstration project.

Implementing Semantic Data Products: A Comprehensive Blueprint for Success As we conclude our series on semantic data products, let's put all the pieces… | 15 comments on LinkedIn

Knowledge Graph / Concept Model: Same or Different? In my understanding when people say 'knowledge graph' they are usually talking about something OWL/RDF-ish,… | 42 comments on LinkedIn

💡 The relevance, trustworthiness and quality of AI and #GenAI applications is increasingly dependent on the quality of enterprise private data and documents…

1. Where does a knowledge graph fit in an enterprise data architecture? A knowledge graph typically sits above data entry/storage systems and below data consumption/visualization systems.

Just learned yesterday that GNOME has been using SPARQL in desktop search for quite a while—and I had no idea! 😲 Turns out their tool, "Tracker", is powered…

🚀 PyG 2.6 is here! 🎉 We’re excited to announce the release of PyG 2.6.0, packed with incredible updates for graph learning! Here’s a quick rundown of what’s… | 14 comments on LinkedIn

Your first ontology doesn’t need to be an ontology. Here’s what I mean. Combining ontologies with knowledge graphs is a powerful approach. But implementing… | 21 comments on LinkedIn

Elevating RAG accuracy and performance by structuring long documents into explorable graphs and implementing graph-based agent systems

Graph neural networks (GNNs) are a type of neural network capable of learning on graph-structured data. However, training GNNs on large-scale graphs is challenging due to iterative aggregations of...

Hey Knowledge Graph friends! As I imagine some of you are, I've been a bit annoyed that many "Knowledge Graph and AI" demos and tools—while definitely… | 13 comments on LinkedIn

How do you maintain an ontology over time? Today, I had a wonderful meeting with Kurt Cagle about ontologies, AI, and beyond. We spent some time on this… | 27 comments on LinkedIn

Design patterns for improving GenAI applications with a graph.

Finding the perfect GraphRAG pattern demands experimentation with different retrieval patterns

Pushing AI On-Device with GraphRAG 🚀. Contribute to trustgraph-ai/trustgraph development by creating an account on GitHub.

#Alhamdulillah, Our iText2KG has achieved over 300 stars and 27 forks in just 10 days after its release, and it is currently ranked among the top 12 trending…

Your first ontology doesn’t need to be an ontology. Here’s what I mean. Combining ontologies with knowledge graphs is a powerful approach. But implementing…

Web Ontology Language (OWL) emerges as a superior choice for knowledge representation in generative AI, offering unparalleled expressiveness, reasoning capabilities, and semantic richness. By leveraging OWL-based knowledge graphs, AI systems can generate more accurate, context-aware, and nuanced outputs across diverse ...

As the volume of digital content increases, the ability to manage it becomes more important. Taxonomy and metadata are vital to finding products, conducting scientific research, and keeping track of organizational information. They also enable a wide variety of analytics on unstructured data. We can see the results of a well-designed taxonomy, but behind the scenes, there's a lot more going on than meets the eye.

My presentation at the "First International Workshop on Scaling Knowledge Graphs for Industry" at the SEMANTICS 2024 Conference in Amsterdam was focused on the…